日本の研究者らは、手の甲と握り拳の写真を解析することでアクロメガリーを検知する人工知能モデルを開発したと述べている。この手法は顔画像や指紋の使用を避けるよう設計されている。チームによると、このシステムは試験で良好な成績を収め、臨床医が潜在的な症例を早期に特定し患者を専門医の評価に回すのに役立つ可能性がある。
アクロメガリーはまれな内分泌疾患で、通常成人期に発症し、体が過剰な成長ホルモンを産生する疾患であり、最も多く下垂体腫瘍が原因である。この疾患は、手足の進行性の拡大、顔貌の変化、骨や臓器の成長への広範な影響を引き起こす可能性がある。
X（旧Twitter）での神戸大学の手の写真によるアクロメガリー検知AIへの初期反応は肯定的で限定的である。ユーザーは顔や指紋を避けたプライバシー配慮のアプローチを称賛し、発見を魅力的と呼び、従来法より早期診断の可能性を強調している。大学リポジトリが査読済み研究を共有した。
Wonderful to see medical researchers so conscientious about patient privacyhttps://t.co/9BRK4BdEm6
— Sharon Polsky MAPP (@PolskySays) 2026年3月4日
Fascinating findings from Japan with AI and hand images in the world of acromegaly. https://t.co/FVUAykd9PT
— AI_4_Healthcare (@AI_4_Healthcare) 2026年3月3日
【Kernel】学術成果を公開しました。
— Kernel ~Kobe Univ. Repository~ (@kobekernel) 2026年3月3日
Automatic acromegaly detection using deep learning on hand images: a multicenter observational study
(著: Nishio Mizuho et al.)https://t.co/zgJnnoZlWQ
A simple hand photo may be the key to detecting a serious disease
— The Something Guy 🇿🇦 (@thesomethingguy) 2026年3月4日
Researchers at Kobe University have developed an AI system that can detect acromegaly, a rare hormone disorder, by analyzing photos of the back of the hand and a clenched fist. The disease often develops slowly…
Researchers at Kobe University develop an AI tool using hand photos to diagnose acromegaly, reducing the years-long delay in identifying this hormone disorder. https://t.co/pHDdR9wjy4
— Galvin (@galvin_8386) 2026年3月4日
AIによるレポート AIによって生成された画像 事実確認済み
A study published March 24, 2026 in *Radiology* reports that AI-generated “deepfake” X-rays can be convincing enough to mislead radiologists and several multimodal AI systems. In testing, radiologists’ average accuracy rose from 41% when they were not told fakes were included to 75% when they were warned, highlighting potential risks for medical imaging security and clinical decision-making.
Scientists at the European Molecular Biology Laboratory (EMBL) in Heidelberg have created an AI-powered tool named MAGIC to identify cells with early chromosomal abnormalities linked to cancer. This system automates the detection of micronuclei, small DNA-containing structures that signal potential cancer development. The technology verifies a theory proposed over a century ago by Theodor Boveri.
AIによるレポート
Researchers at the University of Geneva have developed MangroveGS, an AI model that predicts cancer metastasis risk with nearly 80% accuracy. The tool analyzes gene expression patterns in tumor cells, initially from colon cancer, and applies to other types like breast and lung. Published in Cell Reports, it aims to enable more personalized treatments.
A new research paper demonstrates that large language models can identify real identities behind anonymous online usernames with high accuracy. The method, costing as little as $4 per person, analyzes posts for clues and cross-references them across the internet. Researchers from ETH Zurich, Anthropic, and MATS warn of reduced online privacy.
AIによるレポート
For decades diabetes diagnosis has depended on blood sugar measurements crossing a set threshold. Researchers now worry this method misses millions of people already developing the disease. Better detection tools are in development to address these shortcomings.